Bipedal walking energy minimization by reinforcement learning with evolving policy parameterization
Authors:
Open Access
- 1 September 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21530858,p. 318-324
Abstract
We present a learning-based approach for minimizing the electric energy consumption during walking of a passively-compliant bipedal robot. The energy consumption is reduced by learning a varying-height center-of-mass trajectory which uses efficiently the robot's passive compliance. To do this, we propose a reinforcement learning method which evolves the policy parameterization dynamically during the learning process and thus manages to find better policies faster than by using fixed parameterization. The method is first tested on a function approximation task, and then applied to the humanoid robot COMAN where it achieves significant energy reduction.Keywords
This publication has 18 references indexed in Scilit:
- Learning the skill of archery by a humanoid robot iCub2010
- Adaptive-resolution reinforcement learning with polynomial exploration in deterministic domainsMachine Learning, 2010
- Energy and torque efficient ZMP-based bipedal walking with varying center of mass height2010
- A unified control frame for stable bipedal walking2009
- Learning Biped LocomotionIEEE Robotics & Automation Magazine, 2007
- Learning at the level of synergies for a robot weightlifterRobotics and Autonomous Systems, 2006
- A reinforcement learning scheme for acquisition of via-point representation of human motion2005
- Reinforcement learning with via-point representationNeural Networks, 2004
- A Fast Dynamically Equilibrated Walking Trajectory Generation Method of Humanoid RobotAutonomous Robots, 2002
- The parti-game algorithm for variable resolution reinforcement learning in multidimensional state-spacesMachine Learning, 1995